{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:R6LICOI77ZF3EJQPBNDLZJ47YB","short_pith_number":"pith:R6LICOI7","schema_version":"1.0","canonical_sha256":"8f9681391ffe4bb2260f0b46bca79fc073a9cdf90916521fd8c6164f5bfb7c32","source":{"kind":"arxiv","id":"2312.01058","version":1},"attestation_state":"computed","paper":{"title":"A Survey of Progress on Cooperative Multi-agent Reinforcement Learning in Open Environment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Cong Guan, Lei Yuan, Lihe Li, Yang Yu, Ziqian Zhang","submitted_at":"2023-12-02T08:04:31Z","abstract_excerpt":"Multi-agent Reinforcement Learning (MARL) has gained wide attention in recent years and has made progress in various fields. Specifically, cooperative MARL focuses on training a team of agents to cooperatively achieve tasks that are difficult for a single agent to handle. It has shown great potential in applications such as path planning, autonomous driving, active voltage control, and dynamic algorithm configuration. One of the research focuses in the field of cooperative MARL is how to improve the coordination efficiency of the system, while research work has mainly been conducted in simple,"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2312.01058","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2023-12-02T08:04:31Z","cross_cats_sorted":[],"title_canon_sha256":"9bbfc42af5fe7e59214889148a4b5cfc52949400ef2c05849af9d70dedf40712","abstract_canon_sha256":"5105b13058dc99d0d4df023dbcd060e9cb5545896f035479a1681bb3ba0555ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:19:28.491527Z","signature_b64":"LHmtojzHBuz56lVCBhOj3zw1hrG/lAPjoLvd4p3IEv5fsMLERLZkzUfQkXHdp/IoJGRSpluau8GnOiKN8cHbBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f9681391ffe4bb2260f0b46bca79fc073a9cdf90916521fd8c6164f5bfb7c32","last_reissued_at":"2026-07-05T07:19:28.491019Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:19:28.491019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of Progress on Cooperative Multi-agent Reinforcement Learning in Open Environment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Cong Guan, Lei Yuan, Lihe Li, Yang Yu, Ziqian Zhang","submitted_at":"2023-12-02T08:04:31Z","abstract_excerpt":"Multi-agent Reinforcement Learning (MARL) has gained wide attention in recent years and has made progress in various fields. Specifically, cooperative MARL focuses on training a team of agents to cooperatively achieve tasks that are difficult for a single agent to handle. It has shown great potential in applications such as path planning, autonomous driving, active voltage control, and dynamic algorithm configuration. One of the research focuses in the field of cooperative MARL is how to improve the coordination efficiency of the system, while research work has mainly been conducted in simple,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.01058","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2312.01058/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2312.01058","created_at":"2026-07-05T07:19:28.491079+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.01058v1","created_at":"2026-07-05T07:19:28.491079+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.01058","created_at":"2026-07-05T07:19:28.491079+00:00"},{"alias_kind":"pith_short_12","alias_value":"R6LICOI77ZF3","created_at":"2026-07-05T07:19:28.491079+00:00"},{"alias_kind":"pith_short_16","alias_value":"R6LICOI77ZF3EJQP","created_at":"2026-07-05T07:19:28.491079+00:00"},{"alias_kind":"pith_short_8","alias_value":"R6LICOI7","created_at":"2026-07-05T07:19:28.491079+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25389","citing_title":"Offline Multi-agent Continual Cooperation via Skill Partition and Reuse","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24428","citing_title":"Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08533","citing_title":"Autonomous Aerial Manipulation via Contextual Contrastive Meta Reinforcement Learning","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08102","citing_title":"Continual Quadruped Robots Coordination via Semantic Skill Discovery","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08064","citing_title":"Cooperative Long Rope Skipping via Multi-Agent Reinforcement Learning","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10377","citing_title":"PC3D: Zero-Shot Cooperation Across Variable Rosters via Personalized Context Distillation","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06595","citing_title":"Cross-Modal Navigation with Multi-Agent Reinforcement Learning","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18133","citing_title":"Multi-Agent Systems: From Classical Paradigms to Large Foundation Model-Enabled Futures","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13472","citing_title":"Bridging MARL to SARL: An Order-Independent Multi-Agent Transformer via Latent Consensus","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R6LICOI77ZF3EJQPBNDLZJ47YB","json":"https://pith.science/pith/R6LICOI77ZF3EJQPBNDLZJ47YB.json","graph_json":"https://pith.science/api/pith-number/R6LICOI77ZF3EJQPBNDLZJ47YB/graph.json","events_json":"https://pith.science/api/pith-number/R6LICOI77ZF3EJQPBNDLZJ47YB/events.json","paper":"https://pith.science/paper/R6LICOI7"},"agent_actions":{"view_html":"https://pith.science/pith/R6LICOI77ZF3EJQPBNDLZJ47YB","download_json":"https://pith.science/pith/R6LICOI77ZF3EJQPBNDLZJ47YB.json","view_paper":"https://pith.science/paper/R6LICOI7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.01058&json=true","fetch_graph":"https://pith.science/api/pith-number/R6LICOI77ZF3EJQPBNDLZJ47YB/graph.json","fetch_events":"https://pith.science/api/pith-number/R6LICOI77ZF3EJQPBNDLZJ47YB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R6LICOI77ZF3EJQPBNDLZJ47YB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R6LICOI77ZF3EJQPBNDLZJ47YB/action/storage_attestation","attest_author":"https://pith.science/pith/R6LICOI77ZF3EJQPBNDLZJ47YB/action/author_attestation","sign_citation":"https://pith.science/pith/R6LICOI77ZF3EJQPBNDLZJ47YB/action/citation_signature","submit_replication":"https://pith.science/pith/R6LICOI77ZF3EJQPBNDLZJ47YB/action/replication_record"}},"created_at":"2026-07-05T07:19:28.491079+00:00","updated_at":"2026-07-05T07:19:28.491079+00:00"}